CN111165414B - Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology - Google Patents
Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology Download PDFInfo
- Publication number
- CN111165414B CN111165414B CN202010044382.3A CN202010044382A CN111165414B CN 111165414 B CN111165414 B CN 111165414B CN 202010044382 A CN202010044382 A CN 202010044382A CN 111165414 B CN111165414 B CN 111165414B
- Authority
- CN
- China
- Prior art keywords
- feeding
- fish
- digital signal
- signal processor
- circulating water
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000005516 engineering process Methods 0.000 title claims abstract description 23
- 230000009182 swimming Effects 0.000 title claims abstract description 15
- 230000008878 coupling Effects 0.000 title claims abstract description 11
- 238000010168 coupling process Methods 0.000 title claims abstract description 11
- 238000005859 coupling reaction Methods 0.000 title claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 76
- 238000009360 aquaculture Methods 0.000 claims abstract description 32
- 244000144974 aquaculture Species 0.000 claims abstract description 32
- 230000037406 food intake Effects 0.000 claims abstract description 29
- 230000003134 recirculating effect Effects 0.000 claims abstract description 19
- 235000012631 food intake Nutrition 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 12
- 230000003287 optical effect Effects 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 14
- 238000005286 illumination Methods 0.000 claims description 10
- 239000013589 supplement Substances 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 7
- 229910052760 oxygen Inorganic materials 0.000 claims description 7
- 239000001301 oxygen Substances 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 235000016709 nutrition Nutrition 0.000 claims description 5
- 230000036760 body temperature Effects 0.000 claims description 2
- 238000007599 discharging Methods 0.000 claims 1
- 238000006243 chemical reaction Methods 0.000 abstract 1
- 230000000366 juvenile effect Effects 0.000 description 7
- 238000009395 breeding Methods 0.000 description 5
- 230000001488 breeding effect Effects 0.000 description 5
- 238000012840 feeding operation Methods 0.000 description 4
- 230000036528 appetite Effects 0.000 description 3
- 235000019789 appetite Nutrition 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000035764 nutrition Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 208000010824 fish disease Diseases 0.000 description 1
- 235000003642 hunger Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006213 oxygenation reaction Methods 0.000 description 1
- 230000001954 sterilising effect Effects 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/80—Feeding devices
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K63/00—Receptacles for live fish, e.g. aquaria; Terraria
- A01K63/06—Arrangements for heating or lighting in, or attached to, receptacles for live fish
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K63/00—Receptacles for live fish, e.g. aquaria; Terraria
- A01K63/04—Arrangements for treating water specially adapted to receptacles for live fish
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Engineering & Computer Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Biodiversity & Conservation Biology (AREA)
- Zoology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Farming Of Fish And Shellfish (AREA)
Abstract
The invention discloses a swimming type fish self-adaptive feeding device and method based on an optical-acoustic coupling technology, wherein the device comprises a circulating water culture pond, a circulating water treatment system, a feeder, a high-definition waterproof camera, a hydrophone, a digital signal processor and the like; the device mainly utilizes machine vision technology and acoustic technology to combine and carry out accurate analysis of self-adaptation and aassessment to the real-time desire for food intake of fish in the feeding process to this formulates and throws the feeding strategy. The device has a simple structure, the method is accurate and simple, the self-adaptive feeding device and the method are suitable for a recirculating aquaculture mode, and the problems that feed feeding in the existing recirculating aquaculture system is not combined with the actual feeding demand of fishes, so that the feed feeding is unreasonable, the feed utilization rate and conversion rate are low, the growth welfare of the fishes is influenced and the like can be effectively solved.
Description
Technical Field
The invention relates to the technical field of industrial circulating water aquaculture feeding machinery, in particular to a swimming type fish self-adaptive feeding device and method integrating optical and acoustic technologies.
Background
The industrial circulating water culture is a high-density aquaculture form, the requirements on the regulation and control of water quality are very strict, and the feed feeding is an indispensable working link of the circulating water culture every day, so that the influence on water quality parameters is great. At present, the industrial recirculating aquaculture feed feeding mainly depends on two modes of manual feeding and machine regular and quantitative feeding, the feeding amount and the feeding time cannot be automatically adjusted according to the actual hunger degree of the fish, and the feeding amount is not matched with the actual food intake requirement of the fish. When the feeding amount is less than the actual feeding demand of the fishes, the serious food snatching phenomenon can occur, so that the fishes collide with each other and even cause the surface damage of the fishes, in addition, when some fishes with poor food snatching property cannot be eaten for a long time, the growth speed of the fishes is far lower than that of other fishes in a fish swarm, the serious bipolar differentiation is caused, the fishes with damaged surfaces and weak and small fishes are more easily infected with certain fish diseases, the aquaculture water environment bears larger pressure, and the growth of the fishes is adversely affected; when the feeding amount is larger than the actual feeding demand of the fish, not only the breeding cost is increased, but also the redundant feed can seriously pollute the breeding environment, influence the optimal growth state of the fish and restrict the growth welfare of the fish. Therefore, the feeding amount of the feed is consistent with the actual feeding demand of the fish as much as possible, the breeding density is higher when the juvenile fish is bred by the circulating water system, the juvenile fish is weak in individual body and is more sensitive to the growth environment, and the feeding amount of the feed meets the growth requirement of the juvenile fish and creates good growth conditions for the juvenile fish in the breeding production process of the juvenile fish.
The computer vision technology is a technology which can judge the ingestion requirement of fish in real time and is convenient to be matched with a feeding machine for feeding operation, but for juvenile fish, the body size is smaller, when the number of fish in ingestion is smaller and the ingestion activity degree of fish school is weakened, the visual information change generated by the fish in the ingestion process is not very large, the feeding judgment by using a machine vision method is not very accurate, and the defect is more obvious when the illumination condition is not good and the water turbidity is higher. The acoustic technology can gather the audio information that fish produced at the in-process of ingesting, and this acquisition process is not influenced by illumination and water turbidity, and along with the reduction of the fish quantity of ingesting and the reduction of the desire of ingesting, the different frequency sound pressure level of audio frequency can be certain law and change, and the ingestion intensity that can be better in view of the above changes. Based on the problems and the technologies, the invention provides a swimming type self-adaptive fish feeding device based on an optical-acoustic coupling technology, which combines a machine vision technology and an acoustic technology, automatically switches a control mode according to the growth and ingestion requirements of fishes to achieve accurate feeding operation, provides food and nutrition suitable for growth of the fishes, and creates good growth environmental conditions.
Disclosure of Invention
The invention aims to provide an accurate swimming type fish self-adaptive feeding method and device based on the optical-acoustic coupling technology, which automatically adjust the feeding amount and the feeding duration according to the actual food intake requirement of fish and provide good reference and technical support for the reasonable feeding operation of recirculating aquaculture.
The invention discloses a swimming type fish self-adaptive feeding device based on an optical-acoustic coupling technology, which comprises a circulating water culture pond, a circulating water treatment system, a high-definition waterproof camera, a feeder discharge port, a feeder, an LED light supplement lamp, a PLC (programmable logic controller), a digital signal processor, a display and a hydrophone, wherein the circulating water treatment system is connected with the circulating water culture pond;
a circulating water treatment system is arranged outside the circulating water culture pond;
the high-definition waterproof camera is arranged right above the circulating water culture pond and is connected with the input end of the digital signal processor;
the feeding machine is arranged right above the recirculating aquaculture pond, two discharge ports of the feeding machine are respectively arranged on two sides of the high-definition waterproof camera, in addition, a plurality of LED light supplement lamps are also arranged below the feeding machine (for example, six LED light supplement lamps and two discharge ports are uniformly distributed on the circumference below the feeding machine), and in addition, the feeding machine is connected with the output end of the PLC;
the hydrophone is fixed inside the circulating water culture pond and is connected with the input end of the digital signal processor;
the output end of the digital signal processor is simultaneously connected with the input end of the PLC and the display;
the self-adaptive feeding method for swimming fishes by using the device comprises the following steps:
1) the high-definition waterproof camera transmits shot real-time video pictures to the digital signal processor in real time;
2) the digital signal processor preprocesses the received video pictures, extracts the picture information of each frame and performs threshold segmentation on the images; using the "ostetu thresholdValue division method, let g (x) w0 αβ*(u0-u)2+w1 αβ*(u1-u)2When g (x) takes the maximum value, x is the segmentation threshold, foreground points and background points are divided by x, the foreground points with the gray level larger than x are called background points, the background points with the gray level lower than x are called foreground points, w is0Is the ratio of the foreground points to the image, u0Is the gray level mean value of the foreground point; w is a1Is the proportion of the background points in the image, u1Is the mean value of the gray levels of the background points, u ═ w0*u0+w1*u1(ii) a Alpha is the illumination coefficient of the current frame picture, the parameter is determined by the illumination intensity of the culture environment, the value range of alpha is 0-1, the stronger the light is, the larger the value of alpha is, beta is the turbidity coefficient of the culture water body, the parameter is determined by the turbidity degree of the culture water body, the value range of beta is 0-1, the higher the turbidity degree of the culture water body is, the smaller the value of beta is;
3) calculating the number S1 of pixel points which represent fish body information, namely foreground, in the video frame according to the calculated threshold and the segmentation result, if S1 is more than 0.5S, wherein S is the number of all pixel points in the frame picture, inputting a processing result to a PLC (programmable logic controller), and controlling the feeder to work by the PLC for feeding for 10S;
4) after feeding begins, the camera still normally transmits real-time video information to the digital signal processor, the digital signal processor extracts picture information of each frame in the real-time video, and divides each frame into a food intake central area T1 and a food intake edge area T2, wherein the food intake central area T1 takes the center of the circulating water pool as the circle center, and the radius is as follows:wherein r is0Is the radius of the circulating water pond, n is the number of fish cultured in the circulating water culture pond, liIs the body length of the ith fish in the recirculating aquaculture pondmaxThe maximum body length of the fish in the recirculating aquaculture pond; the areas of the culture pond except the ingestion central area are ingestion marginal areas;
5) respectively calculating optical flow between two adjacent video frames in two areas by using dense optical flow algorithmVariation value F1tAnd F2tThe motion vector having coordinates (i, j) in the T1 region is (x)ij,yij) The motion vector having coordinates (i ', j') in the T2 region is set to (x)ij′,yij') the optical flow variation values of the two areas are respectively:
wherein N is1Is the total number of pixels in the T1 region, N2The total number of pixel points in the T2 area; and presenting the dynamic change of the calculated optical flow change value along with the time on a display screen in real time;
6) comparing the two calculated average values of optical flow changes F1 and F2 in the time period t with a feeding center area threshold FT1 and a feeding edge area threshold FT2 respectively;FT1 ═ 1.4 μ F1 ', FT2 ═ 1.2 μ F2', where F1 'and F2' are the mean values of the changes in the optical flows in the region T1 and the region T2, respectively, in the non-feeding state, μ is the water quality comprehensive correction coefficient,wherein T is the standard temperature of the aquaculture water body, and delta T is the difference value between the water body temperature and the standard temperature T; phIs standard PH, delta P of aquaculture waterhThe difference value of the water body PH and the water body standard PH is obtained; doIs standard dissolved oxygen quantity, delta D, of the culture water bodyoThe difference value of the water body dissolved oxygen and the water body standard dissolved oxygen is obtained; if F1 is more than FT1 and F2 is more than FT2, feeding the next time, wherein the feeding time is the same as that of the previous time, and the feeding amount is as follows:wherein m is0The minimum feed feeding amount for meeting the normal growth and nutritional requirements of the fish;
7) if it isOrWhen the feeding is finished, the digital signal processor automatically switches the machine vision control feeding to the acoustic system for feeding control; the method comprises the steps that a hydrophone collects audio information (1500-10T) dB re 1uPa, wherein T is the real-time water temperature; the feeding amount is as follows:
8) if Z is less than ZT, the digital signal controller sends out feeding stopping instruction to PLC, the PLC controls the feeder to stop working, and automatically switches the feeding control system to machine vision to control, and waits for the start of the next feeding work.
The device of the invention adopts a feeder, a PLC, a high-definition waterproof camera, a hydrophone, a digital signal processor, a display and the like to form a complete self-adaptive feeding device, and can automatically switch feeding control modes according to the actual food intake condition of fish, thereby achieving the purpose of intelligent and accurate feeding;
according to the change of actual aquaculture environment light, the LED lamps uniformly distributed around the high-definition waterproof camera are controlled by the PLC, so that not only is a proper illumination condition provided for the self-adaptive feeding system, but also a proper growth light environment can be provided for fishes by automatically adjusting the brightness.
The invention has the beneficial effects that:
the swimming type fish self-adaptive feeding device based on the light-sound coupling is simple in structure and simple and convenient in control mode, not only can be used for judging the actual appetite of fish for ingestion by using a machine vision technology to feed, but also can be automatically switched to the feeding mode controlled by an acoustic technology along with the weakening of the appetite of fish for ingestion to a certain degree, can accurately control the feeding time and feeding amount according to the appetite of fish for ingestion, is particularly suitable for the breeding and feeding process of juvenile fish, focuses more on the welfare problem of fish under the condition of ensuring the nutritional conditions required by fish growth, and can provide good environmental conditions for fish growth.
Drawings
Fig. 1 is a schematic structural diagram of an optical-acoustic coupling swimming type fish self-adaptive feeding device applied to circulating water.
In the figure: 1-a circulating water culture pond; 2-a circulating water treatment system; 3-high-definition waterproof camera; 4-a discharge hole of a feeder; 5-a feeder; 6-LED light supplement lamp; 7-PLC; 8-a digital signal processor; 9-a display screen; 10-hydrophone
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1, the swimming type self-adaptive fish feeding device based on the optical-acoustic coupling technology of the invention is a specific example, and comprises a recirculating aquaculture pond 1, a recirculating water processing system 2, a high-definition waterproof camera 3, a feeder discharge port 4, a feeder 5, an LED fill light 6, a PLC 7, a digital signal processor 8, a display 9 and a hydrophone 10;
the left side outside the recirculating aquaculture pond 1 is provided with the recirculating water treatment system 2, and the recirculating water treatment system 2 conveys aquaculture wastewater to the recirculating water aquaculture pond 1 after a series of operations such as filtration, sterilization, oxygenation and the like, so that the utilization rate of water resources is greatly improved;
the high-definition waterproof camera 3 is arranged right above the middle of the recirculating aquaculture pond 1 and fixed right below the feeder 5, and the high-definition waterproof camera 3 is connected with the input end of the digital signal processor 8; the installation position of the camera can ensure that the camera can shoot the whole feeding area, and the camera is directly fixed below the feeding machine, so that the assembly and disassembly are convenient, and an additional mounting frame is not needed;
the feeding machine 5 is arranged right above the circulating water culture pond 1, two discharge ports 4 of the feeding machine are respectively arranged on two sides of the high-definition waterproof camera 3, six LED light supplement lamps 6 and the two discharge ports 4 are uniformly distributed on the circumference of the lower part of the feeding machine 5 except for the two discharge ports 4, and in addition, the feeding machine 5 is connected with the output end of the PLC 7; the two feeder discharge ports can ensure that the feed can uniformly cover the whole feeding area, the feeding area is properly enlarged, and the installation position of the LED light supplement lamp cannot influence the work of the camera and the feeder;
the LED light supplement lamps 6 which are uniformly distributed can change the brightness according to the change of light of the actual culture environment, so that not only can suitable illumination conditions be provided for the self-adaptive feeding system, but also a suitable growth light environment can be provided for fishes.
The hydrophone 10 is fixed at the lower right inside the recirculating aquaculture pond 1 and is connected with the input end of the digital signal processor 8; the hydrophone can collect sound information emitted in the fish feeding process and transmit the sound information to the digital signal processor;
the output end of the digital signal processor 8 is simultaneously connected with the input end of the PLC 7 and the display 9; the digital signal processor receives image information input by the camera and sound information input by the hydrophone and performs corresponding processing, firstly, the real-time eating desire of the fish is analyzed through an image processing technology, whether the feeding machine performs feeding operation or not is determined, if the digital signal processor determines that the eating desire is strong, the feeding process is controlled through a machine vision technology, wherein the feeding process comprises feeding duration and feeding amount, and otherwise, the feeding process is automatically switched to an acoustic technology for control; the digital signal processor transmits the processing result to the PLC on one hand for controlling the feeder to work, and on the other hand, the processing result can be displayed on a display screen, so that the operation is more intuitive.
The self-adaptive feeding method for swimming fishes by using the device comprises the following steps:
1) the high-definition waterproof camera 3 transmits the shot real-time video picture to the digital signal processor 8 in real time;
2) the digital signal processor 8 preprocesses the received video picture, extracts the picture information of each frame, and performs threshold segmentation on the image, so that g (x) is w0 αβ*(u0-u)2+w1 αβ*(u1-u)2So thatg (x) x which obtains the maximum value is the segmentation threshold, wherein w0Is the ratio of the foreground points to the image, u0Is the mean value thereof; w is a1Is the proportion of the background points in the image, u1Is the mean value of u ═ w0*u0+w1*u1(ii) a Alpha is the illumination coefficient of the current frame picture, the parameter y is determined by the illumination intensity of the culture environment, the value range of alpha is 0-1, and the stronger the light, the larger the value of alpha is; beta is a turbidity coefficient of the aquaculture water body, the parameter is determined by the turbidity degree of the aquaculture water body, the value range of beta is 0-1, and the higher the turbidity degree of the aquaculture water body is, the smaller the value of beta is;
3) calculating the number S1 of pixel points representing fish body information in a video frame, if S1 is more than 0.5S, wherein S is the number of all pixel points in a frame picture, inputting a processing result to a PLC (programmable logic controller), controlling the feeder to work by the PLC, feeding for 10S, and judging whether the feeder is fed next time or not according to a result of ingestion activity degree analyzed by the digital signal processor 60S after the feeding is started; the process is as follows:
4) after feeding begins, the camera still normally transmits real-time video information to the digital signal processor, the digital signal processor extracts picture information of each frame in the real-time video, and divides each frame into a food intake central area T1 and a food intake edge area T2, wherein the food intake central area T1 takes the center of the circulating water pool as the circle center, and the radius is as follows:wherein r is0Is the radius of the circulating water pond, n is the number of fish cultured in the circulating water culture pond, liIs the body length of the ith fish in the recirculating aquaculture pondmaxThe maximum body length of the fish in the recirculating aquaculture pond; the areas of the culture pond except the ingestion central area are ingestion marginal areas;
5) respectively calculating optical flow change values F1 between two adjacent video frames of two areas by using a dense optical flow algorithmtAnd F2tThe motion vector having coordinates (i, j) in the T1 region is (x)ij,yij) The motion vector having coordinates (i ', j') in the T2 region is set to (x)ij′,yij') the optical flow variation values of the two areas are respectively:
wherein N is1Is the total number of pixels in the T1 region, N2The total number of pixel points in the T2 area; and presenting the dynamic change of the calculated optical flow change value along with the time on a display screen in real time;
6) comparing the two calculated average values of optical flow changes F1 and F2 in the time period t with a feeding center area threshold FT1 and a feeding edge area threshold FT2 respectively;FT1 is 1.4 mu F1 ', FT2 is 1.2 mu F2', wherein F1 'and F2' are light stream change mean values of a region T1 and a region T2 in a non-feeding state respectively, and mu is a water quality comprehensive correction coefficient and is related to various factors such as the temperature, the PH value and the oxygen content of the aquaculture water body; if F1 is more than FT1 and F2 is more than FT2, feeding the next time, wherein the feeding process is the same as the first time, and the feeding amount is as follows:wherein m is0The feed feeding quality is satisfied when the fish grow normally and the nutrition is required;
7) if it isOrWhen the feeding is finished, the digital signal processor automatically switches the machine vision control feeding to the acoustic system for feeding control; the hydrophone collects the audio information (1500-3000Hz) generated in the fish feeding process and transmits the audio information to the digital signal processor in real time, and when the collected audio sound pressure level effective value Z >, the audio information is transmitted to the digital signal processorWhen ZT is given, the system feeds, wherein ZT is threshold value for determining effective value of audio sound pressure level of fed audio, and ZT is (60 log)10T) dB re 1uPa, wherein T is the real-time water temperature; the feeding amount is as follows:
8) if Z is less than ZT, the digital signal controller sends out feeding stopping instruction to PLC, the PLC controls the feeder to stop working, and automatically switches the feeding control system to machine vision to control, and waits for the start of the next feeding work.
The above disclosure is only for the specific embodiment of the present invention, but the present invention is not limited thereto, and it should be understood by those skilled in the art that the modifications made without departing from the present invention shall fall within the protection scope of the present invention.
Claims (1)
1. A self-adaptive swimming type fish feeding method based on an optical-acoustic coupling technology is characterized in that the self-adaptive swimming type fish feeding method based on the optical-acoustic coupling technology is realized by a self-adaptive swimming type fish feeding device which comprises a circulating water culture pond (1), a circulating water treatment system (2), a high-definition waterproof camera (3), a feeder discharge hole (4), a feeder (5), an LED light supplement lamp (6), a PLC (7), a digital signal processor (8), a display (9) and a hydrophone (10);
a circulating water treatment system (2) is arranged outside the circulating water culture pond (1);
the high-definition waterproof camera (3) is arranged right above the circulating water culture pond (1), and the high-definition waterproof camera (3) is connected with the input end of the digital signal processor (8);
the feeding machine (5) is arranged right above the circulating water culture pond (1), the two sides of the high-definition waterproof camera (3) are respectively provided with a discharging hole (4) of the feeding machine, in addition, a plurality of LED light supplement lamps (6) are further arranged below the feeding machine (5), and the feeding machine (5) is connected with the output end of the PLC (7);
the hydrophone (10) is fixed inside the circulating water culture pond (1) and is connected with the input end of the digital signal processor (8);
the output end of the digital signal processor (8) is simultaneously connected with the input end of the PLC (7) and the display (9);
the self-adaptive feeding method comprises the following steps:
1) the high-definition waterproof camera (3) transmits the shot real-time video picture to the digital signal processor (8) in real time;
2) the digital signal processor (8) preprocesses the received video pictures, extracts the picture information of each frame and performs threshold segmentation on the images; let g (x) w0 αβ*(u0-u)2+w1 αβ*(u1-u)2When g (x) takes the maximum value, x is the segmentation threshold, where w0Is the ratio of the foreground points to the image, u0Is the gray level mean value of the foreground point; w is a1Is the proportion of the background points in the image, u1Is the mean value of the gray levels of the background points, u ═ w0*u0+w1*u1(ii) a Alpha is the illumination coefficient of the current frame picture, the parameter is determined by the illumination intensity of the culture environment, the value range of alpha is 0-1, and the stronger the light, the larger the value of alpha; beta is a turbidity coefficient of the aquaculture water body, the parameter is determined by the turbidity degree of the aquaculture water body, the value range of beta is 0-1, and the higher the turbidity degree of the aquaculture water body is, the smaller the value of beta is;
3) according to the segmentation result, calculating the number S1 of pixel points which represent fish body information, namely the foreground, in the video frame, if S1 is more than 0.5S, wherein S is the number of all pixel points in the frame picture, inputting a processing result to a PLC (programmable logic controller), and controlling a feeder to work by the PLC for feeding for 10S;
4) after feeding begins, the camera still normally transmits real-time video information to the digital signal processor, the digital signal processor extracts picture information of each frame in the real-time video, and divides each frame into a food intake central area T1 and a food intake edge area T2, wherein the food intake central area T1 takes the center of the circulating water pool as the circle center, and the radius is as follows:wherein r is0Is the radius of the circulating water pond, and n is the number of fish cultured in the circulating water culture pond,liIs the body length of the ith fish in the recirculating aquaculture pondmaxThe maximum body length of the fish in the recirculating aquaculture pond; the areas of the culture pond except the ingestion central area are ingestion marginal areas;
5) respectively calculating optical flow change values F1 between two adjacent video frames of two areas by using a dense optical flow algorithmtAnd F2tThe motion vector having coordinates (i, j) in the T1 region is (x)ij,yij) The motion vector having coordinates (i ', j') in the T2 region is set to (x)ij′,yij') the optical flow variation values of the two areas are respectively:
wherein N is1Is the total number of pixels in the T1 region, N2The total number of pixel points in the T2 area; and presenting the dynamic change of the calculated optical flow change value along with the time on a display screen in real time;
6) comparing the two calculated average values of optical flow changes F1 and F2 in the time period t with a feeding center area threshold FT1 and a feeding edge area threshold FT2 respectively;FT1 ═ 1.4 μ F1 ', FT2 ═ 1.2 μ F2', where F1 'and F2' are the mean values of the changes in the optical flows in the region T1 and the region T2, respectively, in the non-feeding state, μ is the water quality comprehensive correction coefficient,wherein T is the standard temperature of the aquaculture water body, and delta T is the difference value between the water body temperature and the standard temperature T; phIs standard PH, delta P of aquaculture waterhThe difference value of the water body PH and the water body standard PH is obtained; doIs standard dissolved oxygen quantity, delta D, of the culture water bodyoThe difference value of the water body dissolved oxygen and the water body standard dissolved oxygen is obtained; if F1>FT1 and F2<FT2, then the next feeding is carried out, the feeding time length is the same as the previous feeding, and the feeding amount is:wherein m is0The minimum feed feeding amount for meeting the normal growth and nutritional requirements of the fish;
7) if it isOrWhen the feeding is finished, the digital signal processor automatically switches the machine vision control feeding to the acoustic system for feeding control; the hydrophone collects audio information of 1500-3000Hz generated in the fish feeding process, transmits the audio information to the digital signal processor in real time, and when the collected audio sound pressure level effective value Z>When ZT is given, the system feeds, wherein ZT is threshold value for determining effective value of audio sound pressure level of fed audio, and ZT is (60 log)10T) dB re 1uPa, wherein T is the real-time water temperature; the feeding amount is as follows:
8) if Z is less than ZT, the digital signal controller sends a feeding stopping instruction to PLC, the PLC controls the feeder to stop working, and automatically switches the feeding control system to the machine vision to control, and waits for the start of the next feeding work.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010044382.3A CN111165414B (en) | 2020-01-15 | 2020-01-15 | Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology |
PCT/CN2021/071839 WO2021143783A1 (en) | 2020-01-15 | 2021-01-14 | Swimming-type fish self-adaptive feeding device and method based on light-sound coupling technique |
US17/329,174 US20210279860A1 (en) | 2020-01-15 | 2021-05-25 | Adaptive Feeding Device and Method for Swimming Fish Based on Photo-acoustic Coupling Technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010044382.3A CN111165414B (en) | 2020-01-15 | 2020-01-15 | Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111165414A CN111165414A (en) | 2020-05-19 |
CN111165414B true CN111165414B (en) | 2020-11-17 |
Family
ID=70619198
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010044382.3A Active CN111165414B (en) | 2020-01-15 | 2020-01-15 | Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology |
Country Status (3)
Country | Link |
---|---|
US (1) | US20210279860A1 (en) |
CN (1) | CN111165414B (en) |
WO (1) | WO2021143783A1 (en) |
Families Citing this family (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111165414B (en) * | 2020-01-15 | 2020-11-17 | 浙江大学 | Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology |
CN111528143B (en) * | 2020-05-26 | 2021-08-20 | 大连海洋大学 | Fish shoal feeding behavior quantification method, system, device and storage medium |
CN112273310A (en) * | 2020-11-03 | 2021-01-29 | 浙江海洋大学 | Intelligent feeding system for purse net breeding |
CN112400773B (en) * | 2021-01-21 | 2021-04-09 | 南京农业大学 | Greenhouse fry intelligent feeding device and method based on machine vision technology |
CN112790134B (en) * | 2021-02-02 | 2024-06-14 | 山东鲁威海洋科技有限公司 | Swimming type fish self-adaptive feeding device and method based on water surface fluctuation information |
CN112883861B (en) * | 2021-02-07 | 2022-06-14 | 同济大学 | Feedback type bait casting control method based on fine-grained classification of fish school feeding state |
CN112931356B (en) * | 2021-02-09 | 2022-04-15 | 自然资源部第一海洋研究所 | Intelligent on-demand feeding device for aquaculture and operation method |
CN112931355B (en) * | 2021-02-09 | 2022-04-15 | 自然资源部第一海洋研究所 | Method for automatically throwing bait on demand based on acoustic monitoring |
CN112906570A (en) * | 2021-02-20 | 2021-06-04 | 东营市阔海水产科技有限公司 | Aquaculture feeding method, terminal equipment and readable storage medium |
WO2022187940A1 (en) * | 2021-03-07 | 2022-09-15 | ReelData Inc. | Ai based feeding system and method for land based fish farms |
CN113040081B (en) * | 2021-03-24 | 2022-01-18 | 浙江大学 | Recirculating aquaculture fish feeding decision-making system based on fish shoal swimming energy consumption analysis |
JP7077496B1 (en) | 2021-03-26 | 2022-05-31 | 株式会社マイスティア | Feeding system, feeding method, and sound determination model |
CN113170758B (en) * | 2021-04-21 | 2022-05-03 | 浙江大学 | Variable-speed flow intelligent control system based on fish shoal behaviors and bottom pollution discharge characteristics |
US11297247B1 (en) | 2021-05-03 | 2022-04-05 | X Development Llc | Automated camera positioning for feeding behavior monitoring |
CN113749030B (en) * | 2021-09-09 | 2022-07-15 | 浙江大学 | Fish welfare self-adaptive feeding system suitable for circulating water aquaculture mode |
CN114097675B (en) * | 2021-09-29 | 2023-10-27 | 中国水产科学研究院南海水产研究所深圳试验基地 | Automatic vertical shrimp culture device and culture method |
CN113854221B (en) * | 2021-10-29 | 2022-11-18 | 广州市蓝得生命科技有限公司 | Intelligent feeding control system |
CN114128650B (en) * | 2021-12-15 | 2023-03-21 | 上海海洋大学 | Screening method of comprehensive stress-resistant floating fish |
CN114926490B (en) * | 2022-05-26 | 2024-07-16 | 浙江大学 | Dissolved oxygen early warning method and system based on grouper stress behaviours |
CN114982697A (en) * | 2022-05-31 | 2022-09-02 | 上海海洋大学 | Multi-nutrition-level three-dimensional partition type pond culture system |
CN115861906B (en) * | 2023-03-01 | 2023-05-26 | 北京市农林科学院信息技术研究中心 | Method, device and system for identifying feeding strength of fish shoal and bait casting machine |
CN116616238B (en) * | 2023-04-10 | 2024-04-26 | 浙江大学 | Vision-based self-adaptive feeding method for prawns |
CN116863322B (en) * | 2023-07-28 | 2024-04-30 | 江苏中水东泽农业发展股份有限公司 | Self-adaptive illumination method, device and storage medium for fish breeding based on AI |
CN117581815B (en) * | 2023-12-28 | 2024-06-11 | 佛山市南海区杰大饲料有限公司 | Method and device for judging growth condition of industrial cultured fish |
CN117689491B (en) * | 2024-02-02 | 2024-05-07 | 正大农业科学研究有限公司 | Automatic shrimp feed throwing method, device, system, electronic equipment and storage medium |
CN118446594A (en) * | 2024-07-04 | 2024-08-06 | 中国水产科学研究院南海水产研究所 | Dongxing spot cultivation management method and system based on circulating water optimization |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103070126A (en) * | 2013-01-17 | 2013-05-01 | 中国水产科学研究院渔业机械仪器研究所 | Pond culture sound control feeding method and device based on same |
CN203087272U (en) * | 2013-03-17 | 2013-07-31 | 吴钟华 | Assisted growth device for fishery cultivation |
CN104621021A (en) * | 2015-03-05 | 2015-05-20 | 浙江大学 | Automatic fish feeding rhythm detecting device and method based on computer vision technology |
CN106371485A (en) * | 2016-11-01 | 2017-02-01 | 玉林师范学院 | Intelligent aquaculture system and method based on LABVIEW remote monitoring and control technology |
WO2017204661A2 (en) * | 2016-05-25 | 2017-11-30 | Akvapartner As | Device for supplying feed under water to a floating sea pen |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100725272B1 (en) * | 2006-03-17 | 2007-06-04 | 부경대학교 산학협력단 | Control system and method of sound feeding apparatus for ocean farm |
CN104542411B (en) * | 2014-12-19 | 2016-06-29 | 浙江大学 | A kind of intelligent bait-laying device for fish based on image processing techniques and method |
CN205052519U (en) * | 2015-10-19 | 2016-03-02 | 浙江大学 | Fish, accurate system of feeding of shrimp intelligence |
CN106614243B (en) * | 2016-09-13 | 2019-05-21 | 浙江大学 | A kind of efficient dirt collection and intelligent feeding system for pond circulation flowing water culture |
CN107960362A (en) * | 2017-12-29 | 2018-04-27 | 成都智泉世纪科技有限公司 | Feeding equipment and feeding method |
CN111165414B (en) * | 2020-01-15 | 2020-11-17 | 浙江大学 | Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology |
-
2020
- 2020-01-15 CN CN202010044382.3A patent/CN111165414B/en active Active
-
2021
- 2021-01-14 WO PCT/CN2021/071839 patent/WO2021143783A1/en active Application Filing
- 2021-05-25 US US17/329,174 patent/US20210279860A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103070126A (en) * | 2013-01-17 | 2013-05-01 | 中国水产科学研究院渔业机械仪器研究所 | Pond culture sound control feeding method and device based on same |
CN203087272U (en) * | 2013-03-17 | 2013-07-31 | 吴钟华 | Assisted growth device for fishery cultivation |
CN104621021A (en) * | 2015-03-05 | 2015-05-20 | 浙江大学 | Automatic fish feeding rhythm detecting device and method based on computer vision technology |
WO2017204661A2 (en) * | 2016-05-25 | 2017-11-30 | Akvapartner As | Device for supplying feed under water to a floating sea pen |
CN106371485A (en) * | 2016-11-01 | 2017-02-01 | 玉林师范学院 | Intelligent aquaculture system and method based on LABVIEW remote monitoring and control technology |
Also Published As
Publication number | Publication date |
---|---|
WO2021143783A1 (en) | 2021-07-22 |
US20210279860A1 (en) | 2021-09-09 |
CN111165414A (en) | 2020-05-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111165414B (en) | Swimming type fish self-adaptive feeding device and method based on light-sound coupling technology | |
CN107094683B (en) | Automatic feeding and water quality monitoring control system for aquaculture | |
CN113040081B (en) | Recirculating aquaculture fish feeding decision-making system based on fish shoal swimming energy consumption analysis | |
JPH09262040A (en) | Automatic feeder for aquatic organism and automatic feeding therefor | |
US6615767B1 (en) | Aquaculture method and system for producing aquatic species | |
CN110074030A (en) | A kind of reaction type pond circulation water intelligent feeding system merging machine vision and infrared detection technology | |
CN112790134B (en) | Swimming type fish self-adaptive feeding device and method based on water surface fluctuation information | |
CN112400773B (en) | Greenhouse fry intelligent feeding device and method based on machine vision technology | |
CN104621021A (en) | Automatic fish feeding rhythm detecting device and method based on computer vision technology | |
CN111443744A (en) | Recirculating aquaculture variable-speed flow intelligent control system based on fish shoal behavior and ammonia discharge law feedback | |
CN113749030B (en) | Fish welfare self-adaptive feeding system suitable for circulating water aquaculture mode | |
CN109757419A (en) | A kind of intelligent feeding system and method based on fish meal consumption | |
CN111567464A (en) | Bait throwing control system | |
CN106614243B (en) | A kind of efficient dirt collection and intelligent feeding system for pond circulation flowing water culture | |
CN113951196A (en) | Intelligent feeding method and device based on machine vision and environment dynamic coupling | |
CN110089477A (en) | A kind of fish welfare intelligent cultivation system and method for circulating water cultivation mode | |
CN111261261B (en) | Online intelligent sensing and blending method for coarse cereal rice raw material proportion | |
CN111528164A (en) | Turtle and fish ecological polyculture underwater feeding device | |
CN1618317A (en) | Composite fish bait for fry of brill | |
CN209660186U (en) | A kind of intelligent feeder based on fish meal consumption | |
CN116616238B (en) | Vision-based self-adaptive feeding method for prawns | |
CN115250986A (en) | Fish culture control system based on machine vision | |
CN113892450A (en) | Method for culturing small yellow croakers in deep water net cages | |
CN212576900U (en) | Wheat infection scab disease grain rate online detection system based on embedded deep learning | |
CN114375879A (en) | Breeding method for promoting gonad development of parent fish of yellow-lipped |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |